Linear Location of Acoustic Emission Source Based on LS-SVR and NGA

Abstract:

To solve the fatigue damage location problem of helicopter moving component, a new approach for linear location of acoustic emission (AE) source based on least squares support vector machine for regression (LS-SVR) and niche genetic algorithm (NGA) was proposed. Several time domain parameters of AE signal were taken as the inputs, and the linear coordinates of the breakpoints as the output. The sharing function based niche genetic algorithm is used to select the LS-SVR parameters automatically. The results of pencil lead break location experiment on specimen of carbon fiber materials indicate that the proposed approach can implement linear location of AE source effectively, and has better performance on convergence rate and location accuracy than RBF and BP neural network.

• Periodical: Applied Mechanics and Materials (Volumes 80-81)
• Pages: 302-306
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.80-81.302
• Online since: July 2011
• Authors: Jing Tao Yu, Ming Li Ding, Qi Wang
• Keywords: Acoustic Emission (AE), Linear Location, LS-SVR, Niche Genetic Algorithm, Pencil Lead Break Experiment

References

[1] Ennaceur C, Laksimi A, Herve C. etc. Monitoring crack growth in pressure vessel steels by the acoustic emission technique and the method of potential difference. International Journal of Pressure Vessels and Piping, vol 83, Mar 2006, pp.197-204.

DOI: 10.1016/j.ijpvp.2005.12.004

[2] Nivesrangsan P , Steel J A , Reuben R L. Source location of acoustic emission in diesel engines [J]. Mechanical Systems and Signal Processing. vol 21, Feb 2007, pp.1103-1114.

DOI: 10.1016/j.ymssp.2005.12.010

[3] Wang Xianghong, Zhu Changming, Mao Hanling, Huang Zhenfeng. Source Location of Cracks of Turbine Blades Based on Wavelet Neural Network. vol 47, Aug 2008，pp.1301-1304, 1309.

[4] Wang X. H, Mao H. L, Zhu C.M. Damage localization in hydraulic turbine blades using kernel-independent component analysis and support vector machines. Journal of Mechanical Engineering Science. vol 223, Jan 2009, pp.525-529.

DOI: 10.1243/09544062jmes1296

[5] Wang Xiaodong, Zhang Haoran, Zhang Changjiang , et al, Time series prediction using LS-SVM with particle swarm optimization. Lecture Notes in Computer Science. vol 3972, Mar 2006, pp.747-752.

DOI: 10.1007/11760023_110

[6] Sun Wei, Yang Chenguang. Research of least square support vector machine based on chaotic time series in power load forecasting model. Lecture Notes in Computer Science. vol 4233, Feb 2006, pp.984-993.

DOI: 10.1007/11893257_108

[7] Wei Wei, Qi Wang, Hua Wang, Hong Guang Zhang. The feature extraction of nonparametric curves based on niche genetic algorithms and multi-population competition. Pattern. Recognition Letters. vol 26, Jul 2005, pp.1483-1497.

DOI: 10.1016/j.patrec.2004.10.027